Tools for Semi-automatic Preparation of Training Data for OCR.
Ladislav LencJirí MartínekPavel KrálPublished in: AIAI (2019)
Keyphrases
- semi automatic
- training data
- fully automatic
- semi automatically
- gold standard
- data sets
- training set
- domain ontology
- design rationale
- medical knowledge
- document images
- labor intensive
- optical character recognition
- landmark extraction
- wrapper generation
- ontology mapping
- character recognition
- semantic annotation
- post processing
- learning algorithm
- supervised learning
- decision trees
- metadata
- artificial intelligence